检索
E-mail
RSS

作者投稿 主编审稿 专家审稿 远程编辑

热带海洋学报

• • 上一篇    下一篇

基于浮标海浪谱的数据驱动风矢量反演方法研究

刘宁1, 2, 李昱达1，党超群1, 2，王斌1, 2，袁瑞峰1, 2   

  1. 1.国家海洋技术中心, 天津  300112;

    2.自然资源部海洋观测技术重点实验室, 天津 300112

  • 收稿日期:2026-04-21 修回日期:2026-05-21 接受日期:2026-06-22
  • 通讯作者: 王斌
  • 基金资助:
    自然资源部海洋观测技术重点实验室基金项目(2022klootB01); 三亚市科技创新专项项目(2022KJCX96)

Data-Driven Wind Vector Retrieval from Buoy Wave Spectra

LIU Ning1, 2, LI Yuda1, DANG Chaoqun1, 2, WANG Bin1, 2, YUAN Ruifeng1, 2    

  1. 1. National Ocean Technology Center, Tianjin 300112, China;


    2. Key Laboratory of Ocean Observation Technology, MNR, Tianjin 300112, China;


  • Received:2026-04-21 Revised:2026-05-21 Accepted:2026-06-22
  • Supported by:
    Research Fund of the Key Laboratory of Ocean Observation Technology MNR (No. 2025KLOOTB02)； Sanya Science and Technology Innovation Special Project (No. 2022KJCX96)

PDF (PC)

赞

摘要： 海浪谱高频尾部的能量水平与海面风应力存在物理耦合，为基于海浪观测反演风场参数提供了理论基础。然而混合浪条件下传统经验方法的精度受限，而现有DNN(deep neural network)仅能对单一频点进行特征提取，难以挖掘波浪谱不同频点间的关联信息，为此本文引入卷积操作，实现对波浪谱各频点间隐含特征的全局提取。本文以NDBC(national data buoy center)浮标观测数据为基础，构建MobileNetV4-1D面向海浪谱时序特征的轻量级端到端回归框架，实现风速与风向的同步反演。随后，将物理经验方法、DNN模型与MobileNetV4-1D模型开展对比实验，系统评估各方法在风场反演任务中的精度与稳健性，尤其重点模拟实际业务中模型面对未来未知月份数据的预测场景，实验结果表明，MobileNetV4-1D的时序泛化性能显著优于DNN：风速反演RMSE(root mean square error)降至1.43m·s-1（降低9.0%），风向反演RMSE降至31.06°（降低32.7%）。该研究证实，适配后的MobileNetV4-1D模型在保证反演精度的同时，具备更强的时序泛化性能，为海洋风场反演的业务化应用提供了可靠的技术支撑与理论参考。

关键词: 波浪谱, 风场反演, MobileNetV4, 一维卷积

Abstract: The energy level in the high-frequency tail of the ocean wave spectrum is physically coupled with sea surface wind stress, which provides a theoretical foundation for wind field parameter inversion based on ocean wave observations. Nevertheless, the accuracy of traditional empirical methods is limited under mixed sea conditions. Furthermore, existing deep neural network (DNN) models only extract features from individual frequency points and fail to exploit the correlation information among different frequencies of the wave spectrum. Accordingly, convolutional operations are introduced in this paper to globally extract the implicit inter-frequency features of the wave spectrum.Based on the in-situ observational data from the National Data Buoy Center (NDBC), a lightweight end-to-end regression framework named MobileNetV4-1D is constructed for temporal feature mining of ocean wave spectra, to realize synchronous inversion of wind speed and wind direction. Subsequently, comparative experiments are conducted among physical empirical methods, conventional DNN models and the proposed MobileNetV4-1D model to systematically evaluate their inversion accuracy and robustness in wind field retrieval. In particular, the prediction scenario of models on unknown future monthly data in practical operational applications is emphatically simulated. The experimental results demonstrate that the temporal generalization performance of MobileNetV4-1D is significantly superior to that of the conventional DNN: the root mean square error (RMSE) of wind speed inversion is reduced to 1.43 m⋅s−1 (a decrease of 9.0%), and the RMSE of wind direction inversion is lowered to 31.06°(a decrease of 32.7%). This study verifies that the adapted MobileNetV4-1D model achieves favorable inversion accuracy with enhanced temporal generalization ability, which provides reliable technical support and theoretical references for the operational application of ocean wind field inversion.

Key words: wave spectrum, inverse wind, MobileNetV4, one-dimensional convolution